LPI Radar Signal Recognition Based on Dual-Channel CNN and Feature Fusion
The accuracy of low probability of intercept (LPI) radar waveform recognition is an important and challenging problem in electronic warfare. Aiming at the problem of the difficulty in feature extraction and the low recognition rates of the LPI radar signal under a low signal-to-noise ratio, and insp...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/14/3/570 |
| _version_ | 1797441585589256192 |
|---|---|
| author | Daying Quan Zeyu Tang Xiaofeng Wang Wenchao Zhai Chongxiao Qu |
| author_facet | Daying Quan Zeyu Tang Xiaofeng Wang Wenchao Zhai Chongxiao Qu |
| author_sort | Daying Quan |
| collection | DOAJ |
| description | The accuracy of low probability of intercept (LPI) radar waveform recognition is an important and challenging problem in electronic warfare. Aiming at the problem of the difficulty in feature extraction and the low recognition rates of the LPI radar signal under a low signal-to-noise ratio, and inspired by the symmetry theory, we propose a new approach for the LPI radar signal recognition method based on a dual-channel convolutional neural network (CNN) and feature fusion. Our new approach contains three main modules: the preprocessing module that converts the LPI radar waveforms into two-dimensional time-frequency images using the Choi–Williams distribution (CWD) transformation and performs image binarization, the feature extraction module that extracts different features obtained from the images, and the recognition module that utilizes a multi-layer perceptron (MLP) network to fuse these features and distinguish the type of LPI radar signals. In the feature extraction module, a two-channel CNN model is proposed that extracts Histogram of Oriented Gradients (HOG) features and deep features from time-frequency images, respectively. Finally, the recognition module recognizes the radar signals using a Softmax classifier based on the fused features from two channels. The experimental results from 12 types of LPI radar signals prove the superiority and robustness of the proposed model. Its overall recognition rate reaches 97% when the signal-to-noise ratio is −6 dB. |
| first_indexed | 2024-03-09T12:25:17Z |
| format | Article |
| id | doaj.art-e365a6d81fb5408da2c009e68ca28e64 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-09T12:25:17Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-e365a6d81fb5408da2c009e68ca28e642023-11-30T22:36:28ZengMDPI AGSymmetry2073-89942022-03-0114357010.3390/sym14030570LPI Radar Signal Recognition Based on Dual-Channel CNN and Feature FusionDaying Quan0Zeyu Tang1Xiaofeng Wang2Wenchao Zhai3Chongxiao Qu4Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaThe 52nd Research Institute of China Electronics Technology Group, Hangzhou 311121, ChinaThe accuracy of low probability of intercept (LPI) radar waveform recognition is an important and challenging problem in electronic warfare. Aiming at the problem of the difficulty in feature extraction and the low recognition rates of the LPI radar signal under a low signal-to-noise ratio, and inspired by the symmetry theory, we propose a new approach for the LPI radar signal recognition method based on a dual-channel convolutional neural network (CNN) and feature fusion. Our new approach contains three main modules: the preprocessing module that converts the LPI radar waveforms into two-dimensional time-frequency images using the Choi–Williams distribution (CWD) transformation and performs image binarization, the feature extraction module that extracts different features obtained from the images, and the recognition module that utilizes a multi-layer perceptron (MLP) network to fuse these features and distinguish the type of LPI radar signals. In the feature extraction module, a two-channel CNN model is proposed that extracts Histogram of Oriented Gradients (HOG) features and deep features from time-frequency images, respectively. Finally, the recognition module recognizes the radar signals using a Softmax classifier based on the fused features from two channels. The experimental results from 12 types of LPI radar signals prove the superiority and robustness of the proposed model. Its overall recognition rate reaches 97% when the signal-to-noise ratio is −6 dB.https://www.mdpi.com/2073-8994/14/3/570LPI radar signalCWD time-frequency analysisCNNHOGsignal recognition |
| spellingShingle | Daying Quan Zeyu Tang Xiaofeng Wang Wenchao Zhai Chongxiao Qu LPI Radar Signal Recognition Based on Dual-Channel CNN and Feature Fusion Symmetry LPI radar signal CWD time-frequency analysis CNN HOG signal recognition |
| title | LPI Radar Signal Recognition Based on Dual-Channel CNN and Feature Fusion |
| title_full | LPI Radar Signal Recognition Based on Dual-Channel CNN and Feature Fusion |
| title_fullStr | LPI Radar Signal Recognition Based on Dual-Channel CNN and Feature Fusion |
| title_full_unstemmed | LPI Radar Signal Recognition Based on Dual-Channel CNN and Feature Fusion |
| title_short | LPI Radar Signal Recognition Based on Dual-Channel CNN and Feature Fusion |
| title_sort | lpi radar signal recognition based on dual channel cnn and feature fusion |
| topic | LPI radar signal CWD time-frequency analysis CNN HOG signal recognition |
| url | https://www.mdpi.com/2073-8994/14/3/570 |
| work_keys_str_mv | AT dayingquan lpiradarsignalrecognitionbasedondualchannelcnnandfeaturefusion AT zeyutang lpiradarsignalrecognitionbasedondualchannelcnnandfeaturefusion AT xiaofengwang lpiradarsignalrecognitionbasedondualchannelcnnandfeaturefusion AT wenchaozhai lpiradarsignalrecognitionbasedondualchannelcnnandfeaturefusion AT chongxiaoqu lpiradarsignalrecognitionbasedondualchannelcnnandfeaturefusion |